Uploaded July 2026 | Updated September 2026, 3 weeks ago
Want ChatGPT-level AI without sending your data to the cloud? This guide walks through installing Ollama on Windows so you can run large language models locally β private, offline, and free. You'll see the full setup: install, settings, storage/GPU considerations, and how to download and switch between models.
π Ollama download: ollama.com/download
π Model library: ollama.com/library
Key takeaways:
Ollama runs open-source LLMs locally on Windows, Mac, or Linux
Disk space and GPU determine install size and response speed
Settings let you control model storage location, context length, network exposure, and auto-updates
Models can be pulled from the built-in dropdown or via PowerShell (ollama pull [model])
You can install and switch between multiple models freely
===============================
Time Stamps
00:00 - Local AI Demo (Hook)
00:23 - What You'll Learn
00:25 - Downloading Ollama for Windows
00:44 - Installing Ollama
00:48 - Storage and GPU Requirements
01:03 - Ollama Dashboard Overview
01:19 - Settings Walkthrough
01:46 - Setting Model Storage Location
01:59 - Context Length Explained
02:20 - Using the Chat Interface
02:57 - Downloading a Different Model
03:24 - Pulling a Model via PowerShell
03:56 - Switching Between Models
04:21 - Wrap Up
===============================
Connect with Me
βΆ Email: youtube@geekrar.com
βΆ Blog: geekrar.com
βΆ Twitter: twitter.com/Geekrar
My Other Channels
π¬ @GEEKrarGuides
π¬ @CryptoJar
Want ChatGPT-level AI without sending your data to the cloud? This guide walks through installing Ollama on Windows so you can run large language models locally β private, offline, and free. You'll see the full setup: install, settings, storage/GPU considerations, and how to download and switch between models.
π Ollama download: ollama.com/download
π Model library: ollama.com/library
Key takeaways:
Ollama runs open-source LLMs locally on Windows, Mac, or Linux
Disk space and GPU determine install size and response speed
Settings let you control model storage location, context length, network exposure, and auto-updates
Models can be pulled from the built-in dropdown or via PowerShell (ollama pull [model])
You can install and switch between multiple models freely
===============================
Time Stamps
00:00 - Local AI Demo (Hook)
00:23 - What You'll Learn
00:25 - Downloading Ollama for Windows
00:44 - Installing Ollama
00:48 - Storage and GPU Requirements
01:03 - Ollama Dashboard Overview
01:19 - Settings Walkthrough
01:46 - Setting Model Storage Location
01:59 - Context Length Explained
02:20 - Using the Chat Interface
02:57 - Downloading a Different Model
03:24 - Pulling a Model via PowerShell
03:56 - Switching Between Models
04:21 - Wrap Up
===============================
Connect with Me
βΆ Email: youtube@geekrar.com
βΆ Blog: geekrar.com
βΆ Twitter: twitter.com/Geekrar
My Other Channels
π¬ @GEEKrarGuides
π¬ @CryptoJar










